Blackwell Bank Card Hub MCP
Enables users to explore and manage banking card features including product discovery, comparison, eligibility checks, spend insights, merchant offers, travel notices, card controls, and digital wallet provisioning.
README
Blackwell Bank Card Hub MCP App
A ChatGPT Apps / MCP demo for a retail banking card experience. The app opens on a Card Hub and lets users move between product discovery, comparison, eligibility, spend insights, merchant offers, travel notices, card controls, and wallet provisioning.
Public deployment:
https://bank.myareareport.com/mcp
The VPS deployment is isolated from the existing mcp.myareareport.com service. This app runs in its own Docker Compose service named mcp-bank and is bound locally on 127.0.0.1:3002.
Features
- Card Hub-first embedded UI with persistent customer/card context.
- Product catalogue with card details, rewards calculator, balance transfer estimator, and eligibility flow.
- Mobile tabs for
Cards,Compare, andEligibility. - Visual comparison summary for travel, everyday spend, and credit building.
- Servicing tools for spend insights, merchant offers, travel notices, card controls, and digital wallet.
- App-only MCP tools for UI navigation and interactive state changes.
- Streamable HTTP transport for hosted MCP clients.
- Stdio transport for local desktop MCP clients.
Requirements
- Node.js 22 recommended, Node.js 18+ minimum.
- npm.
- Docker and Docker Compose for VPS/container deployment.
Local Setup
git clone https://github.com/meabs/mcp-app-ui-bank.git
cd mcp-app-ui-bank
npm install
npm run build
npm start
The local MCP endpoint runs at:
http://localhost:3001/mcp
For development watch mode:
npm run dev
Scripts
| Command | Purpose |
|---|---|
npm run build |
Build the single-file app bundle with Vite. |
npm start |
Build and start the Streamable HTTP MCP server. |
npm run start:stdio |
Start the MCP server over stdio. |
npm run dev |
Watch-build the UI and restart the server on changes. |
npm test |
Run the Node test suite. |
Testing
Run the automated tests:
npm test
Build the app:
npm run build
Check production dependencies:
npm audit --omit=dev
Verify a running MCP endpoint:
curl -fsS http://localhost:3001/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1"}},"id":1}'
List tools:
curl -fsS http://localhost:3001/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","method":"tools/list","params":{},"id":2}'
Public MCP URL
Use this endpoint when adding the app to a ChatGPT MCP-capable project or tool configuration:
https://bank.myareareport.com/mcp
The deployed server should report:
Blackwell Bank Card Services
Docker Deployment
The included Compose file builds the app and exposes the container only on localhost:
docker compose up -d --build
Container mapping:
mcp-bank: 127.0.0.1:3002 -> 3001/tcp
Cloudflare Tunnel routes bank.myareareport.com to http://localhost:3002.
Key Files
| File | Purpose |
|---|---|
src/index.js |
Streamable HTTP and stdio transport setup. |
src/server.js |
MCP tool and resource registrations. |
src/demo-data.js |
Demo card, hub, eligibility, spend, wallet, and offer data. |
src/mcp-app.html |
Embedded app shell and view containers. |
src/mcp-app.js |
App state, routing, host integration, and product flow rendering. |
src/feature-views.js |
Hub, compare, servicing, calculator, and journey renderers. |
src/mcp-app.css |
Embedded app visual system and responsive layout. |
docker-compose.yml |
Isolated VPS service definition for mcp-bank. |
Current Verification
Latest known-good checks:
npm test
npm run build
npm audit --omit=dev
The deployed endpoint at https://bank.myareareport.com/mcp initializes and exposes the Blackwell Bank tools.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。